init
Browse files- feature_extractor/preprocessor_config.json +20 -0
- logs/dreambooth/1669210244.6340702/events.out.tfevents.1669210244.yfl-diffusion-jqbcl-829218-worker-0.417508.1 +3 -0
- logs/dreambooth/1669210244.6453846/hparams.yml +37 -0
- logs/dreambooth/events.out.tfevents.1669210244.yfl-diffusion-jqbcl-829218-worker-0.417508.0 +3 -0
- model_index.json +32 -0
- safety_checker/config.json +179 -0
- safety_checker/pytorch_model.bin +3 -0
- scheduler/scheduler_config.json +13 -0
- text_encoder/config.json +32 -0
- text_encoder/pytorch_model.bin +3 -0
- tokenizer/sentencepiece.bpe.model +3 -0
- tokenizer/special_tokens_map.json +15 -0
- tokenizer/tokenizer_config.json +22 -0
- unet/config.json +37 -0
- unet/diffusion_pytorch_model.bin +3 -0
- vae/config.json +30 -0
- vae/diffusion_pytorch_model.bin +3 -0
feature_extractor/preprocessor_config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"crop_size": 224,
|
3 |
+
"do_center_crop": true,
|
4 |
+
"do_convert_rgb": true,
|
5 |
+
"do_normalize": true,
|
6 |
+
"do_resize": true,
|
7 |
+
"feature_extractor_type": "CLIPFeatureExtractor",
|
8 |
+
"image_mean": [
|
9 |
+
0.48145466,
|
10 |
+
0.4578275,
|
11 |
+
0.40821073
|
12 |
+
],
|
13 |
+
"image_std": [
|
14 |
+
0.26862954,
|
15 |
+
0.26130258,
|
16 |
+
0.27577711
|
17 |
+
],
|
18 |
+
"resample": 3,
|
19 |
+
"size": 224
|
20 |
+
}
|
logs/dreambooth/1669210244.6340702/events.out.tfevents.1669210244.yfl-diffusion-jqbcl-829218-worker-0.417508.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a8f0a8db313dc914f7b5cbd951706e7f618bbc2a8f43466b74a8e8803108159
|
3 |
+
size 1992
|
logs/dreambooth/1669210244.6453846/hparams.yml
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
adam_beta1: 0.9
|
2 |
+
adam_beta2: 0.999
|
3 |
+
adam_epsilon: 1.0e-08
|
4 |
+
adam_weight_decay: 0.01
|
5 |
+
center_crop: false
|
6 |
+
class_data_dir: ../../prior_mingren_dreambooth
|
7 |
+
class_prompt: "\u4E00\u5F20\u7537\u5B69\u7684\u7167\u7247"
|
8 |
+
gradient_accumulation_steps: 1
|
9 |
+
gradient_checkpointing: false
|
10 |
+
hub_model_id: null
|
11 |
+
hub_token: null
|
12 |
+
instance_data_dir: ../../mingren
|
13 |
+
instance_prompt: "\u4E00\u5F20<\u9E23\u4EBA>\u7537\u5B69\u7684\u7167\u7247"
|
14 |
+
learning_rate: 5.0e-06
|
15 |
+
local_rank: -1
|
16 |
+
logging_dir: logs
|
17 |
+
lr_scheduler: constant
|
18 |
+
lr_warmup_steps: 0
|
19 |
+
max_grad_norm: 1.0
|
20 |
+
max_train_steps: 1200
|
21 |
+
mixed_precision: 'no'
|
22 |
+
num_class_images: 200
|
23 |
+
num_train_epochs: 6
|
24 |
+
output_dir: ./alt_ckpt_mingren_with_prior_loss
|
25 |
+
pretrained_model_name_or_path: BAAI/AltDiffusion-m9
|
26 |
+
prior_loss_weight: 1.0
|
27 |
+
push_to_hub: false
|
28 |
+
resolution: 512
|
29 |
+
revision: null
|
30 |
+
sample_batch_size: 4
|
31 |
+
scale_lr: false
|
32 |
+
seed: null
|
33 |
+
tokenizer_name: null
|
34 |
+
train_batch_size: 1
|
35 |
+
train_text_encoder: false
|
36 |
+
use_8bit_adam: false
|
37 |
+
with_prior_preservation: true
|
logs/dreambooth/events.out.tfevents.1669210244.yfl-diffusion-jqbcl-829218-worker-0.417508.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9fd9c56569c80dc0f6ad579a7da4ab665c6ed647044d98d711f78f3b244609ac
|
3 |
+
size 100586
|
model_index.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "AltDiffusionPipeline",
|
3 |
+
"_diffusers_version": "0.8.0.dev0",
|
4 |
+
"feature_extractor": [
|
5 |
+
"transformers",
|
6 |
+
"CLIPFeatureExtractor"
|
7 |
+
],
|
8 |
+
"safety_checker": [
|
9 |
+
"stable_diffusion",
|
10 |
+
"StableDiffusionSafetyChecker"
|
11 |
+
],
|
12 |
+
"scheduler": [
|
13 |
+
"diffusers",
|
14 |
+
"PNDMScheduler"
|
15 |
+
],
|
16 |
+
"text_encoder": [
|
17 |
+
"alt_diffusion",
|
18 |
+
"RobertaSeriesModelWithTransformation"
|
19 |
+
],
|
20 |
+
"tokenizer": [
|
21 |
+
"transformers",
|
22 |
+
"XLMRobertaTokenizer"
|
23 |
+
],
|
24 |
+
"unet": [
|
25 |
+
"diffusers",
|
26 |
+
"UNet2DConditionModel"
|
27 |
+
],
|
28 |
+
"vae": [
|
29 |
+
"diffusers",
|
30 |
+
"AutoencoderKL"
|
31 |
+
]
|
32 |
+
}
|
safety_checker/config.json
ADDED
@@ -0,0 +1,179 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_commit_hash": "bf1a6105ac03ca3b13224fda20220a12d9bc7607",
|
3 |
+
"_name_or_path": "/root/.cache/huggingface/diffusers/models--BAAI--AltDiffusion-m9/snapshots/bf1a6105ac03ca3b13224fda20220a12d9bc7607/safety_checker",
|
4 |
+
"architectures": [
|
5 |
+
"StableDiffusionSafetyChecker"
|
6 |
+
],
|
7 |
+
"initializer_factor": 1.0,
|
8 |
+
"logit_scale_init_value": 2.6592,
|
9 |
+
"model_type": "clip",
|
10 |
+
"projection_dim": 768,
|
11 |
+
"text_config": {
|
12 |
+
"_name_or_path": "",
|
13 |
+
"add_cross_attention": false,
|
14 |
+
"architectures": null,
|
15 |
+
"attention_dropout": 0.0,
|
16 |
+
"bad_words_ids": null,
|
17 |
+
"begin_suppress_tokens": null,
|
18 |
+
"bos_token_id": 0,
|
19 |
+
"chunk_size_feed_forward": 0,
|
20 |
+
"cross_attention_hidden_size": null,
|
21 |
+
"decoder_start_token_id": null,
|
22 |
+
"diversity_penalty": 0.0,
|
23 |
+
"do_sample": false,
|
24 |
+
"dropout": 0.0,
|
25 |
+
"early_stopping": false,
|
26 |
+
"encoder_no_repeat_ngram_size": 0,
|
27 |
+
"eos_token_id": 2,
|
28 |
+
"exponential_decay_length_penalty": null,
|
29 |
+
"finetuning_task": null,
|
30 |
+
"forced_bos_token_id": null,
|
31 |
+
"forced_eos_token_id": null,
|
32 |
+
"hidden_act": "quick_gelu",
|
33 |
+
"hidden_size": 768,
|
34 |
+
"id2label": {
|
35 |
+
"0": "LABEL_0",
|
36 |
+
"1": "LABEL_1"
|
37 |
+
},
|
38 |
+
"initializer_factor": 1.0,
|
39 |
+
"initializer_range": 0.02,
|
40 |
+
"intermediate_size": 3072,
|
41 |
+
"is_decoder": false,
|
42 |
+
"is_encoder_decoder": false,
|
43 |
+
"label2id": {
|
44 |
+
"LABEL_0": 0,
|
45 |
+
"LABEL_1": 1
|
46 |
+
},
|
47 |
+
"layer_norm_eps": 1e-05,
|
48 |
+
"length_penalty": 1.0,
|
49 |
+
"max_length": 20,
|
50 |
+
"max_position_embeddings": 77,
|
51 |
+
"min_length": 0,
|
52 |
+
"model_type": "clip_text_model",
|
53 |
+
"no_repeat_ngram_size": 0,
|
54 |
+
"num_attention_heads": 12,
|
55 |
+
"num_beam_groups": 1,
|
56 |
+
"num_beams": 1,
|
57 |
+
"num_hidden_layers": 12,
|
58 |
+
"num_return_sequences": 1,
|
59 |
+
"output_attentions": false,
|
60 |
+
"output_hidden_states": false,
|
61 |
+
"output_scores": false,
|
62 |
+
"pad_token_id": 1,
|
63 |
+
"prefix": null,
|
64 |
+
"problem_type": null,
|
65 |
+
"pruned_heads": {},
|
66 |
+
"remove_invalid_values": false,
|
67 |
+
"repetition_penalty": 1.0,
|
68 |
+
"return_dict": true,
|
69 |
+
"return_dict_in_generate": false,
|
70 |
+
"sep_token_id": null,
|
71 |
+
"suppress_tokens": null,
|
72 |
+
"task_specific_params": null,
|
73 |
+
"temperature": 1.0,
|
74 |
+
"tf_legacy_loss": false,
|
75 |
+
"tie_encoder_decoder": false,
|
76 |
+
"tie_word_embeddings": true,
|
77 |
+
"tokenizer_class": null,
|
78 |
+
"top_k": 50,
|
79 |
+
"top_p": 1.0,
|
80 |
+
"torch_dtype": null,
|
81 |
+
"torchscript": false,
|
82 |
+
"transformers_version": "4.24.0",
|
83 |
+
"typical_p": 1.0,
|
84 |
+
"use_bfloat16": false,
|
85 |
+
"vocab_size": 49408
|
86 |
+
},
|
87 |
+
"text_config_dict": {
|
88 |
+
"hidden_size": 768,
|
89 |
+
"intermediate_size": 3072,
|
90 |
+
"num_attention_heads": 12,
|
91 |
+
"num_hidden_layers": 12
|
92 |
+
},
|
93 |
+
"torch_dtype": "float32",
|
94 |
+
"transformers_version": null,
|
95 |
+
"vision_config": {
|
96 |
+
"_name_or_path": "",
|
97 |
+
"add_cross_attention": false,
|
98 |
+
"architectures": null,
|
99 |
+
"attention_dropout": 0.0,
|
100 |
+
"bad_words_ids": null,
|
101 |
+
"begin_suppress_tokens": null,
|
102 |
+
"bos_token_id": null,
|
103 |
+
"chunk_size_feed_forward": 0,
|
104 |
+
"cross_attention_hidden_size": null,
|
105 |
+
"decoder_start_token_id": null,
|
106 |
+
"diversity_penalty": 0.0,
|
107 |
+
"do_sample": false,
|
108 |
+
"dropout": 0.0,
|
109 |
+
"early_stopping": false,
|
110 |
+
"encoder_no_repeat_ngram_size": 0,
|
111 |
+
"eos_token_id": null,
|
112 |
+
"exponential_decay_length_penalty": null,
|
113 |
+
"finetuning_task": null,
|
114 |
+
"forced_bos_token_id": null,
|
115 |
+
"forced_eos_token_id": null,
|
116 |
+
"hidden_act": "quick_gelu",
|
117 |
+
"hidden_size": 1024,
|
118 |
+
"id2label": {
|
119 |
+
"0": "LABEL_0",
|
120 |
+
"1": "LABEL_1"
|
121 |
+
},
|
122 |
+
"image_size": 224,
|
123 |
+
"initializer_factor": 1.0,
|
124 |
+
"initializer_range": 0.02,
|
125 |
+
"intermediate_size": 4096,
|
126 |
+
"is_decoder": false,
|
127 |
+
"is_encoder_decoder": false,
|
128 |
+
"label2id": {
|
129 |
+
"LABEL_0": 0,
|
130 |
+
"LABEL_1": 1
|
131 |
+
},
|
132 |
+
"layer_norm_eps": 1e-05,
|
133 |
+
"length_penalty": 1.0,
|
134 |
+
"max_length": 20,
|
135 |
+
"min_length": 0,
|
136 |
+
"model_type": "clip_vision_model",
|
137 |
+
"no_repeat_ngram_size": 0,
|
138 |
+
"num_attention_heads": 16,
|
139 |
+
"num_beam_groups": 1,
|
140 |
+
"num_beams": 1,
|
141 |
+
"num_channels": 3,
|
142 |
+
"num_hidden_layers": 24,
|
143 |
+
"num_return_sequences": 1,
|
144 |
+
"output_attentions": false,
|
145 |
+
"output_hidden_states": false,
|
146 |
+
"output_scores": false,
|
147 |
+
"pad_token_id": null,
|
148 |
+
"patch_size": 14,
|
149 |
+
"prefix": null,
|
150 |
+
"problem_type": null,
|
151 |
+
"pruned_heads": {},
|
152 |
+
"remove_invalid_values": false,
|
153 |
+
"repetition_penalty": 1.0,
|
154 |
+
"return_dict": true,
|
155 |
+
"return_dict_in_generate": false,
|
156 |
+
"sep_token_id": null,
|
157 |
+
"suppress_tokens": null,
|
158 |
+
"task_specific_params": null,
|
159 |
+
"temperature": 1.0,
|
160 |
+
"tf_legacy_loss": false,
|
161 |
+
"tie_encoder_decoder": false,
|
162 |
+
"tie_word_embeddings": true,
|
163 |
+
"tokenizer_class": null,
|
164 |
+
"top_k": 50,
|
165 |
+
"top_p": 1.0,
|
166 |
+
"torch_dtype": null,
|
167 |
+
"torchscript": false,
|
168 |
+
"transformers_version": "4.24.0",
|
169 |
+
"typical_p": 1.0,
|
170 |
+
"use_bfloat16": false
|
171 |
+
},
|
172 |
+
"vision_config_dict": {
|
173 |
+
"hidden_size": 1024,
|
174 |
+
"intermediate_size": 4096,
|
175 |
+
"num_attention_heads": 16,
|
176 |
+
"num_hidden_layers": 24,
|
177 |
+
"patch_size": 14
|
178 |
+
}
|
179 |
+
}
|
safety_checker/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16d28f2b37109f222cdc33620fdd262102ac32112be0352a7f77e9614b35a394
|
3 |
+
size 1216064769
|
scheduler/scheduler_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "PNDMScheduler",
|
3 |
+
"_diffusers_version": "0.8.0.dev0",
|
4 |
+
"beta_end": 0.012,
|
5 |
+
"beta_schedule": "scaled_linear",
|
6 |
+
"beta_start": 0.00085,
|
7 |
+
"clip_sample": false,
|
8 |
+
"num_train_timesteps": 1000,
|
9 |
+
"set_alpha_to_one": false,
|
10 |
+
"skip_prk_steps": false,
|
11 |
+
"steps_offset": 1,
|
12 |
+
"trained_betas": null
|
13 |
+
}
|
text_encoder/config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "BAAI/AltDiffusion-m9",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaSeriesModelWithTransformation"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.0,
|
12 |
+
"hidden_size": 1024,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 4096,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"learn_encoder": false,
|
17 |
+
"max_position_embeddings": 514,
|
18 |
+
"model_type": "xlm-roberta",
|
19 |
+
"num_attention_heads": 16,
|
20 |
+
"num_hidden_layers": 24,
|
21 |
+
"output_past": true,
|
22 |
+
"pad_token_id": 1,
|
23 |
+
"pooler_fn": "cls",
|
24 |
+
"position_embedding_type": "absolute",
|
25 |
+
"project_dim": 768,
|
26 |
+
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.24.0",
|
28 |
+
"type_vocab_size": 1,
|
29 |
+
"use_attention_mask": true,
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 250002
|
32 |
+
}
|
text_encoder/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6b6bcf99f0b25c5b22df111517fb09bb6da9b7190804e79d5edbb3ebd005330
|
3 |
+
size 2242850613
|
tokenizer/sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
3 |
+
size 5069051
|
tokenizer/special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer/tokenizer_config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"__type": "AddedToken",
|
7 |
+
"content": "<mask>",
|
8 |
+
"lstrip": true,
|
9 |
+
"normalized": true,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"model_max_length": 512,
|
14 |
+
"name_or_path": "BAAI/AltDiffusion-m9",
|
15 |
+
"pad_token": "<pad>",
|
16 |
+
"processor_class": "CHCLIPProcess",
|
17 |
+
"sep_token": "</s>",
|
18 |
+
"sp_model_kwargs": {},
|
19 |
+
"special_tokens_map_file": null,
|
20 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
21 |
+
"unk_token": "<unk>"
|
22 |
+
}
|
unet/config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.8.0.dev0",
|
4 |
+
"_name_or_path": "BAAI/AltDiffusion-m9",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"attention_head_dim": 8,
|
7 |
+
"block_out_channels": [
|
8 |
+
320,
|
9 |
+
640,
|
10 |
+
1280,
|
11 |
+
1280
|
12 |
+
],
|
13 |
+
"center_input_sample": false,
|
14 |
+
"cross_attention_dim": 768,
|
15 |
+
"down_block_types": [
|
16 |
+
"CrossAttnDownBlock2D",
|
17 |
+
"CrossAttnDownBlock2D",
|
18 |
+
"CrossAttnDownBlock2D",
|
19 |
+
"DownBlock2D"
|
20 |
+
],
|
21 |
+
"downsample_padding": 1,
|
22 |
+
"flip_sin_to_cos": true,
|
23 |
+
"freq_shift": 0,
|
24 |
+
"in_channels": 4,
|
25 |
+
"layers_per_block": 2,
|
26 |
+
"mid_block_scale_factor": 1,
|
27 |
+
"norm_eps": 1e-05,
|
28 |
+
"norm_num_groups": 32,
|
29 |
+
"out_channels": 4,
|
30 |
+
"sample_size": 32,
|
31 |
+
"up_block_types": [
|
32 |
+
"UpBlock2D",
|
33 |
+
"CrossAttnUpBlock2D",
|
34 |
+
"CrossAttnUpBlock2D",
|
35 |
+
"CrossAttnUpBlock2D"
|
36 |
+
]
|
37 |
+
}
|
unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0ad6076075b31d9fc5c6d5153604e72f8b03ae6dcc58839cf10cdd7427379cb
|
3 |
+
size 3438375973
|
vae/config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "AutoencoderKL",
|
3 |
+
"_diffusers_version": "0.8.0.dev0",
|
4 |
+
"_name_or_path": "/root/.cache/huggingface/diffusers/models--BAAI--AltDiffusion-m9/snapshots/bf1a6105ac03ca3b13224fda20220a12d9bc7607/vae",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"block_out_channels": [
|
7 |
+
128,
|
8 |
+
256,
|
9 |
+
512,
|
10 |
+
512
|
11 |
+
],
|
12 |
+
"down_block_types": [
|
13 |
+
"DownEncoderBlock2D",
|
14 |
+
"DownEncoderBlock2D",
|
15 |
+
"DownEncoderBlock2D",
|
16 |
+
"DownEncoderBlock2D"
|
17 |
+
],
|
18 |
+
"in_channels": 3,
|
19 |
+
"latent_channels": 4,
|
20 |
+
"layers_per_block": 2,
|
21 |
+
"norm_num_groups": 32,
|
22 |
+
"out_channels": 3,
|
23 |
+
"sample_size": 512,
|
24 |
+
"up_block_types": [
|
25 |
+
"UpDecoderBlock2D",
|
26 |
+
"UpDecoderBlock2D",
|
27 |
+
"UpDecoderBlock2D",
|
28 |
+
"UpDecoderBlock2D"
|
29 |
+
]
|
30 |
+
}
|
vae/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af27ea858349760ebe3311953e0bfe8d6fd257dc9537ae0b2b938c262132a2c6
|
3 |
+
size 334711857
|